MSD explores applying generative Al to improve the deviation management process using AWS services

This post is co-written with Hossein Salami and Jwalant Vyas from MSD.

In the biopharmaceutical industry, deviations in the manufacturing process are rigorously addressed. Each deviation is thoroughly documented, and its various aspects and potential impacts are closely examined to help ensure drug product quality, patient safety, and compliance. For leading pharmaceutical companies, managing these deviations robustly and efficiently is crucial to maintaining high standards and minimizing disruptions.

Recently, the Digital Manufacturing Data Science team at Merck & Co., Inc., Rahway, NJ, USA (MSD) recognized an opportunity to streamline aspects of their deviation management process using emerging technologies including vector databases and generative AI, powered by AWS services such as Amazon Bedrock and Amazon OpenSearch. This innovative approach aims to use the organization’s past deviations as a vast, diverse, and reliable knowledge source. Such knowledge can potentially help reduce the time and resources required for—and increase the efficiency ...